INDEX

Explanations

phrases related to expansion or growth

oai_token-act-pair · gpt-3.5-turbo

instances of the word "expanded" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĪĴ

-0.77

ndra

-0.76

lihood

-0.76

ÃŃa

-0.74

fell

-0.73

ched

-0.72

 Defeat

-0.71

=-=-=-=-=-=-=-=-

-0.71

 Â¯

-0.71

ches

-0.71

POSITIVE LOGITS

 expansion

0.84

 enlarg

0.79

utterstock

0.79

 expansions

0.77

arcer

0.76

ĸļ

0.75

 utilization

0.71

sheets

0.70

ansion

0.70

aucas

0.70

Activations Density 0.017%

phrases related to expansion or growth

instances of the word "expanded" in various contexts

No Comments

No Known Activations